Page 138 - Special Topic Session (STS) - Volume 4
P. 138

STS571 Sarpono et al.



                               Combining mobile phone data and survey data
                                for the best result: Experience from Indonesia
                                           Sarpono, Titi Kanti Lestari
                                              BPS-Statistics Indonesia

                  Abstract
                  Data collection is complicated in Indonesia due to vast geographic distances
                  and difficulty of travel. So is it that the inbound tourism survey for measuring
                  tourism  is  under  coverage.  Improving  the  accuracy  of  inbound  tourism
                  statistics  with  mobile  positioning  data.  Mobile  positioning  data  (MPD)  is
                  considered as one of the most promising big data for measuring the mobility
                  of people, including mobility of tourists based. It holds more information, is
                  much faster and  more  reliable.  However,  as  a  new  data  source,  there also
                  challenges and limitation of big data (including mobile positioning data) that
                  have  to  be  taken  into  account  in  order  to  become  a  valuable  and  quality
                  statistics. In MPD there is a lack of qualitative data on tourism motivation and
                  the  sample  does  not  include  non-roamers.  One  way  to  overcome  the
                  limitations of big data  is by combining it with small data obtained from a
                  survey.  This  paper  shows  that  combining  big  and  small  data  will  provide
                  optimal results. We used mobile positioning data about roaming activities of
                  cross-border tourists in Indonesia at border areas and mobile usage survey
                  conducted at the borders in order to know the motivations for cross-border
                  movements  (both  roamers  and  non-roamers).  Then,  we  come  up  with  the
                  formula that combines big and small data to obtain the best result for tourism
                  statistics.

                  Keywords
                  Big Data, tourism statistics, remote area

                  1.  Introduction
                      Indonesia has a border land with Malaysia, Timor Leste, and Papua New
                  Guinea along 3092.8 km. While, the sea area borders with 10 countries, namely
                  India,  Malaysia,  Singapore,  Thailand,  Vietnam  Philippines,  Australia,Timor
                  Leste, Palau, and Papua New Guinea. This sea border covers 92 leading small
                  island, starting from Miangas Island in the north to Dana Island in the south.
                  During this time foreign tourists were calculated based on the Immigration
                  Office based on the passport swipe, which recorded the traffic of all people
                  entering  Indonesian  territory.  Since  the  vast  condition  of  the  Indonesian
                  territory with diverse border areas (sea and land) and the limitations of the
                  Immigration Office, not all foreign tourists entering Indonesian territory are
                  recorded  regularly  and  on  time.  There  are  still  many  border  regions  of


                                                                     127 | I S I   W S C   2 0 1 9
   133   134   135   136   137   138   139   140   141   142   143